Phoneme recognition based on multi-resolution and non-causal context

摘要

An alternative view of neural-network-based phoneme recognition using multiresolution ideas and noncausal context is suggested. Some suggestions are made regarding target and error weight functions to improve performance and simplify training. Based on these observations, a simple network with self recurrent links of different delays is proposed and tested on the task of speaker- independent recognition of unvoiced plosives, (p,t,k), with input feature vectors derived from an auditory model.